© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13361
    Prev
    Next
    INDEX
    Explanations

    near future occurrences

    oai_token-act-pair · gemini-2.0-flash

    future dates and times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     next
    -3.36
    next
    -3.13
    Next
    -3.02
     Next
    -3.00
     NEXT
    -2.59
    NEXT
    -2.50
     nächste
    -2.06
     nästa
    -2.03
     nächsten
    -2.03
     próxima
    -1.94
    POSITIVE LOGITS
    
    0.60
     Abp
    0.59
    WebVitals
    0.59
     تانيه
    0.54
    zzleHttp
    0.53
     unknownFields
    0.51
     Giochi
    0.51
    🏻‍♀️
    0.50
    eventbus
    0.50
     SwitchCompat
    0.49
    Activations Density 1.621%

    No Known Activations